Han Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Han Xiao has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Jie Zhou
Tsinghua University, Beijing, China
4 shared publications - Jiwen Lu
Tsinghua University
4 shared publications - Ziwei Wang
School of Engineering Lancaster University Lancaster UK
3 shared publications - Gao Wu
Zhejiang University, Hangzhou, China
1 shared publication - Guangyi Liu
Zhejiang University, Hangzhou, China
1 shared publication - Guankun Wang
Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6282-6290
MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6282-6290
Open AccessMemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12636-12643
CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12636-12643
Open AccessCoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection
- 2 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (11) , 5101-5123
Learning Generalizable Mixed-Precision Quantization via Attribution Imitation
- 2 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (11) , 5101-5123
Learning Generalizable Mixed-Precision Quantization via Attribution Imitation
- 13 April 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (7) , 1761-1783
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
- 13 April 2023
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 131 (7) , 1761-1783
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression
- Open Access
Token-Label Alignment for Vision Transformers
Data mixing strategies (e.g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs). They mix two images as inputs for training and assign them with a mixed label with the same ratio. While they are shown effective for vision transformers (ViTs), we identify a token fluctuation phenomenon that has suppressed the potential of data mixing strategies. We empirically observe that the contributions of input tokens fluctuate as forward propagating, which might induce a different mixing ratio in the output tokens. The training target computed by the original data mixing strategy can thus be inaccurate, resulting in less effective training. To address this, we propose a token-label alignment (TL-Align) method to trace the correspondence between transformed tokens and the original tokens to maintain a label for each token. We reuse the computed attention at each layer for efficient token-label alignment, introducing only negligible additional training costs. Extensive experiments demonstrate that our method improves the performance of ViTs on image classification, semantic segmentation, objective detection, and transfer learning tasks. Code is available at: https://github.com/Euphoria16/TL-Align.
Open AccessToken-Label Alignment for Vision Transformers
Data mixing strategies (e.g., CutMix) have shown the ability to greatly improve the performance of convolutional neural networks (CNNs). They mix two images as inputs for training and assign them with a mixed label with the same ratio. While they are shown effective for vision transformers (ViTs), we identify a token fluctuation phenomenon that has suppressed the potential of data mixing strategies. We empirically observe that the contributions of input tokens fluctuate as forward propagating, which might induce a different mixing ratio in the output tokens. The training target computed by the original data mixing strategy can thus be inaccurate, resulting in less effective training. To address this, we propose a token-label alignment (TL-Align) method to trace the correspondence between transformed tokens and the original tokens to maintain a label for each token. We reuse the computed attention at each layer for efficient token-label alignment, introducing only negligible additional training costs. Extensive experiments demonstrate that our method improves the performance of ViTs on image classification, semantic segmentation, objective detection, and transfer learning tasks. Code is available at: https://github.com/Euphoria16/TL-Align.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (2) , 1919-1933
Learning Deep Binary Descriptors via Bitwise Interaction Mining
In this paper, we propose a GraphBit method to learn unsupervised deep binary descriptors for efficient image representation. Conventional binary representation learning methods directly quantize each element according to the threshold without considering the quantization ambiguousness. The elements near the boundary dubbed as “ambiguous bits” fail to collect effective information for reliable binarization and are sensitive to noise that causes reversed bits. We argue that there are implicit inner relationships among bits in binary descriptors called bitwise interaction, where the related bits can provide extra instruction as prior knowledge for ambiguousness reduction. Specifically, we design a deep reinforcement learning model to learn the structure of the graph for bitwise interaction mining, and the uncertainty of binary codes is reduced by maximizing the mutual information with input and related bits. Consequently, the ambiguous bits receive additional instruction from the graph for reliable binarization. Moreover, we further present a differentiable search method (GraphBit+) that mines the bitwise interaction in continuous space, so that the heavy search cost caused by the training difficulties in reinforcement learning is significantly reduced. Since the GraphBit and GraphBit+ methods learn fixed bitwise interaction which is suboptimal for various input, the inaccurate instruction from the fixed bitwise interaction cannot effectively decrease the ambiguousness of binary descriptors. To address this, we further propose the unsupervised binary descriptor learning method via dynamic bitwise interaction mining (D-GraphBit), where a graph convolutional network called GraphMiner reasons the optimal bitwise interaction for each input sample. Extensive experimental results on the CIFAR-10, NUS-WIDE, ImageNet-100, Brown and HPatches datasets demonstrate the efficiency and effectiveness of the proposed GraphBit, GraphBit+ and D-GraphBit.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (2) , 1919-1933
Learning Deep Binary Descriptors via Bitwise Interaction Mining
In this paper, we propose a GraphBit method to learn unsupervised deep binary descriptors for efficient image representation. Conventional binary representation learning methods directly quantize each element according to the threshold without considering the quantization ambiguousness. The elements near the boundary dubbed as “ambiguous bits” fail to collect effective information for reliable binarization and are sensitive to noise that causes reversed bits. We argue that there are implicit inner relationships among bits in binary descriptors called bitwise interaction, where the related bits can provide extra instruction as prior knowledge for ambiguousness reduction. Specifically, we design a deep reinforcement learning model to learn the structure of the graph for bitwise interaction mining, and the uncertainty of binary codes is reduced by maximizing the mutual information with input and related bits. Consequently, the ambiguous bits receive additional instruction from the graph for reliable binarization. Moreover, we further present a differentiable search method (GraphBit+) that mines the bitwise interaction in continuous space, so that the heavy search cost caused by the training difficulties in reinforcement learning is significantly reduced. Since the GraphBit and GraphBit+ methods learn fixed bitwise interaction which is suboptimal for various input, the inaccurate instruction from the fixed bitwise interaction cannot effectively decrease the ambiguousness of binary descriptors. To address this, we further propose the unsupervised binary descriptor learning method via dynamic bitwise interaction mining (D-GraphBit), where a graph convolutional network called GraphMiner reasons the optimal bitwise interaction for each input sample. Extensive experimental results on the CIFAR-10, NUS-WIDE, ImageNet-100, Brown and HPatches datasets demonstrate the efficiency and effectiveness of the proposed GraphBit, GraphBit+ and D-GraphBit.